setwd("F:/wpisz swoja sciezke")

load('dataLeukemia.RData')
#View(data[1:10,1:10])
names(data)[1:10]
unique(data$Leukemia.class)
table(data$Leukemia.class)
set.data=data[data$Leukemia.class=='AML with normal karyotype + other abnormalities' | data$Leukemia.class=='CLL',-c(1,3)]
set.data$Leukemia.class=as.numeric(set.data$Leukemia.class)/6-1
rm(data)
#View(set.data[,1:10])
v=1:length(set.data$Leukemia.class)
index.test=sample(v,round(length(set.data$Leukemia.class)/3))
index.train=v[-index.test]
data.train=set.data[index.train,]
data.test=set.data[index.test,]
result=randomForest(x=data.train[,-1],y=as.factor(data.train[,1]),importance=TRUE)
var.imp=result$importance
var.imp.100=row.names(var.imp[order(var.imp[,4])])

predict(x=data.train[,var.imp.100],y=as.factor(data.train[,1]))
var.pred.test = predict(result, x=data.test[,var.imp.100])
auc(as.factor(data.test[,1]),var.pred.test)

var.imp = result$importance #view(var.imp)
var.imp.100 = row.names(var.imp[order(var.imp[,4],decreasing = TRUE),])[1:100] #view(var.imp)
result2=randomForest(x=data.train[,var.imp.100],y=as.factor(data.train[,2]),importance=TRUE)